给予看：

import re
import string

def count_words(file_name):
    word_count = {}
    with open(file_name, 'r') as input_file:
        for line in input_file:
            if line.startswith("document"):
                doc_id = line.split()[0]
                words = line.strip().split()[1:]
                for word in words:
                    word = word.translate(str.maketrans('','', string.punctuation)).lower()
                    if word in word_count:
                        word_count[word][doc_id] = word_count[word].get(doc_id, 0) + 1
                    else:
                        word_count[word] = {doc_id: 1}
    return word_count

word_count = count_words("documents.txt")
for word, doc_count in word_count.items():
    print(f"{word} appears in: {doc_count}")

您删除了之前的类似问题和我的答案，所以我不确定是否应该再次回答。我将给出一个稍微不同的答案，不带groupby，尽管我认为它是好的。
您可以尝试：

import re
from collections import Counter
from string import punctuation

with open("stopwords_en.txt", "r") as file:
    stopwords = set().union(*(line.rstrip().split() for line in file))
translation = str.maketrans("", "", punctuation)
re_new_doc = re.compile(r"(\d+)\s*$")
with open("documents.txt", "r") as file:
    word_count, doc_no = {}, 0
    for line in file:
        match = re_new_doc.match(line)
        if match:
            doc_no = int(match[1])
            continue
        line = line.translate(translation)
        for word in re.findall(r"\w+", line):
            word = word.casefold()
            if word in stopwords:
                continue
            word_count.setdefault(word, []).append(doc_no)

word_count_overall = {word: len(docs) for word, docs in word_count.items()}
word_count_docs = {word: Counter(docs) for word, docs in word_count.items()}

• 我只会预先制作一次翻译表，而不是为每一行重新制作。
• 用于标识新文档(\d+)\s*$"的正则表达式在行首查找数字，在换行符之前不查找任何其他内容（可能除了一些空格），如果标识符遵循不同的逻辑，则必须调整它。
• word_count将单词的每次出现记录在具有当前文档编号的列表中。
• word_count_overall只取resp.列表的长度来获得单词的总计数。
• word_count_docs确实对列表应用了Counter，以获得每个文档中每个单词的计数。